This role pays more than
52%
of similar roles. Most pay
$214,000–$265,625
— the shaded band above.
At the midpoint, this role pays about
$251k
versus about
$240k
for comparable roles.
Based on 240 similar postings.
Employer
About DoorDash, Inc
DoorDash, Inc. is an American company operating online food ordering and food delivery. It trades under the symbol DASH. With a 56% market share, DoorDash is the largest food delivery platform in the United States.
DoorDash, Inc currently has
187 open roles
on FindRole.
Listed pay typically runs
$144,800–$212,950
across 166 roles with salary data.
Staff Machine Learning Scientist, Applied Causal Inference joins a senior pod of causal ML and econometrics experts to build the causal spine for a large-scale consumer marketplace. This role focuses on developing the causal machine learning foundation for New Verticals, including grocery, retail, and pharmacy categories. You will design and productionize systems such as uplift models, heterogeneous treatment effect models, counterfactual evaluation frameworks, and surrogate metrics to influence decisions in ranking, promotions, and search. The work involves integrating experimentation, observational data, and ML decisioning to solve complex marketplace problems where randomized experiments are often insufficient. Key technical methodologies include doubly robust estimation, double ML, instrumental variables, diff-in-diff, CUPED, contextual bandits, and off-policy evaluation. You will build reliable pipelines and partner with cross-functional teams to translate these advanced causal models into production systems that drive consumer growth and marketplace health.
Design and productionize causal ML systems to influence marketplace decisions across various business verticals.
Build uplift and heterogeneous treatment effect models for consumer lifecycle value, promotions, and retention.
Develop counterfactual evaluation frameworks for ranking, recommendations, search results, and marketplace interventions.
Create systems that integrate experimentation, observational data, and ML decisioning to optimize trade-offs.
Design surrogate metrics and early indicators to accelerate development while maintaining long-term marketplace health.
Apply advanced econometric methods like double ML, IV, and synthetic controls to solve complex problems.
Translate causal models into production systems for ranking, targeting, budget allocation, and inventory management.
Establish standards for causal reasoning and debugging across the broader machine learning organization.
What we're looking for
Deep practical experience with causal inference, econometrics, experimentation, or causal ML.
Experience shipping models or decision systems in production for high-scale settings like marketplaces, ads, or search.
Proficiency in methods including doubly robust estimation, double ML, IV, diff-in-diff, CUPED, uplift modeling, contextual bandits, and off-policy evaluation.
Strong ML engineering ability to build reliable pipelines, train models, and evaluate them rigorously for production.
Ability to design counterfactual evaluation frameworks and surrogate metrics for marketplace decisions.
Strong product judgment to connect causal methods to business outcomes rather than just offline metrics.
Ability to collaborate across functions with engineers, economists, data scientists, and product leaders.